Triple
T9123469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bad Pyrmont |
E218914
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Śrem |
E80187
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Śrem | Statement: [Bad Pyrmont, hasTwinTown, Śrem]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Śrem Context triple: [Bad Pyrmont, hasTwinTown, Śrem]
-
A.
Śrem
chosen
Śrem is a town in western Poland known for its historical architecture, industrial activity, and location on the Warta River in the Greater Poland region.
-
B.
Chełmek
Chełmek is a small town in southern Poland known historically for its shoe industry and its location near Oświęcim (Auschwitz).
-
C.
Śmielec
Śmielec is a mountain peak in the Karkonosze range of the Sudetes on the border between Poland and the Czech Republic.
-
D.
Łeba
Łeba is a river in northern Poland that flows through the Pomeranian region to the Baltic Sea.
-
E.
Krzemień
Krzemień is a prominent mountain peak in Poland’s Bieszczady range, known for its scenic hiking routes and panoramic views of the surrounding Carpathian landscape.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca83dddd548190983b96c664f7f367 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8b5fa188190be6465e74cf26915 |
completed | April 1, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0308ff628819083f02bf71eb40c5b |
completed | April 3, 2026, 9:26 p.m. |
Created at: March 30, 2026, 7:17 p.m.